nlp:retrieval-augmented_methods

Table of Contents

Retrieval-Augmented Methods (RAG)

Retrieval-Augmented Methods (RAG)

Overviews

Gao et al 2023 - Retrieval-Augmented Generation for Large Language Models: A Survey

Papers

Piktus et al 2020 - Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks (Mike Lewis)
Liu et al 2021 - What Makes Good In-Context Examples for GPT-3? Cited by Rubin 2021
Rubin et al 2021 - Learning To Retrieve Prompts for In-Context Learning Is this the first retrieval-based in-context learning paper?
Poesia et al 2022 - Synchromesh: Reliable code generation from pre-trained language models One of the first retrieval-based in-context learning papers
Wang et al 2022 - Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data
Jiang et al 2023 - Active Retrieval Augmented Generation
Izacard et al 2022 - Few-shot Learning with Retrieval Augmented Language Models Learns the retrieval model
Lin et al 2023 - RA-DIT: Retrieval-Augmented Dual Instruction Tuning Fine-tunes a language model so it's better for retrieval augmented use. Best performance occurs after a small number of fine-tuning steps (<500 steps!).
Zhang et al 2024 - Accelerating Retrieval-Augmented Language Model Serving with Speculation
Lu et al 2025 - TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text
Zheng et al 2025 - Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals

During Pre-Training

Related Pages

nlp/retrieval-augmented_methods.txt · Last modified: 2026/08/16 21:40 by jmflanig